{"uid":"cap_PWyJNTu7jAJnVGTjb_0zQ","slug":"sec-intel-agentdiet-dev-web-distillation-with-bm25-budget-control-7ef48554","name":"Web Distillation with BM25 Budget Control","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://sec-intel.agentdiet.dev/v1/paywall-clean-extract)","url":"https://sec-intel.agentdiet.dev/v1/paywall-clean-extract?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","required":["url"],"properties":{"url":{"type":"string","minLength":1,"description":"Target webpage URL to fetch and distill (or builtin://stripe-docs)"},"html":{"type":"string","description":"Optional raw HTML string to distill directly without fetching"},"mode":{"enum":["markdown","structured","skeleton","budget"],"type":"string","default":"markdown","description":"Distillation mode"},"query":{"type":"string","description":"BM25 focus query when mode=budget"},"max_tokens":{"type":"integer","minimum":20,"description":"Strict token budget ceiling when mode=budget"}}},"responseSchema":{"type":"object","required":["status","roi_proof","data"],"properties":{"data":{"type":"object","description":"Distilled Markdown, structured JSON tables/metadata, skeleton outline, or BM25 budget excerpt."},"cache":{"type":"object","properties":{"status":{"enum":["HIT","MISS"],"type":"string"},"cache_key":{"type":"string"},"latency_ms":{"type":"number"}}},"status":{"type":"string","description":"Execution status ('ok')"},"billing":{"type":"object","properties":{"agent_id":{"type":"string"},"payment_method":{"type":"string"},"fee_charged_usd":{"type":"number"}}},"roi_proof":{"type":"object","properties":{"raw_tokens":{"type":"integer"},"tokens_saved":{"type":"integer"},"roi_multiplier":{"type":"number"},"distilled_tokens":{"type":"integer"},"llm_cost_saved_usd":{"type":"number"},"compression_ratio_pct":{"type":"number"}}}}},"example":null,"exampleRequest":null,"tags":[],"displayCostAmount":"0.001","displayCostAsset":"USD","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.001/call","primary":{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_o81epm87Y8woSVb0L4f22","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"sec-intel.agentdiet.dev","brandSlug":"sec-intel-agentdiet-dev-mpp","brandBaseUrl":"https://sec-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or processes raw HTML and distills it into compact Markdown, structured JSON, skeleton outline, or BM25-ranked token-budget excerpt, with ROI compression metrics","exampleAgentPrompt":"Fetch the page at https://stripe.com/docs/payments and distill it into clean markdown using a strict 500-token budget focused on the query 'payment intents API'.","exampleUseCases":[{"title":"Token-efficient research from a live URL","prompt":"Go to https://openai.com/research/gpt-4 and distill it into compact markdown — I only want the key findings, and keep it under 300 tokens."},{"title":"BM25-ranked excerpt for a specific topic","prompt":"Pull the page at https://docs.aws.amazon.com/s3/index.html and give me just the parts most relevant to 'bucket permissions and IAM policies', with a max budget of 400 tokens."},{"title":"Structured data extraction from raw HTML","prompt":"I have this raw HTML from a financial report — can you distill it into structured JSON tables with the key metadata and figures extracted?"}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes optional cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Missing required 'url' field when html is also absent causes a validation error","mode=budget without a 'query' may return unranked or empty excerpt","max_tokens set too low (below 20) is rejected by schema validation","Paywalled or bot-blocked pages may return incomplete or empty distillation","HTML too large or malformed may cause parsing failures","Network timeout fetching remote URL"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read a webpage but wants to minimize LLM token consumption — especially for long, noisy, or heavily-formatted pages. It is the right choice when you need BM25-ranked excerpts focused on a specific query rather than the full page. Prefer it over generic scrapers when compression ratio and ROI proof are important to track. Use the budget mode for strict token caps in cost-sensitive pipelines.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:30:27.702Z","isFirstParty":false,"canonicalSlug":"sec-intel-agentdiet-dev-web-distillation-with-bm25-budget-control-bba76e87"}